Air-ground cooperative unmanned system task allocation method and system based on cooperative game theory

Abstract

The invention discloses an air-ground collaborative unmanned system task allocation method and system based on a cooperative game theory, and the method comprises the steps: analyzing the combat capability, tactical collaboration, viability, economic and functional values and other factors of an unmanned system; and evaluating the relative contribution and benefit distribution of each unmanned system in the cooperative combat task by using the cooperative game theory model. According to the method, firstly, real-time data of each unmanned system is collected, then the utility value of each system under different task allocation schemes is calculated through a game theory model, and then the optimal task allocation scheme is determined. According to the invention, it can be ensured that each unmanned system can exert the maximum efficiency in the task, and the cooperation efficiency and task success rate of the whole system can be ensured at the same time. The method has high adaptability and flexibility, can adapt to variable battlefield environments and task requirements, and provides an effective task allocation strategy for cooperative combat of the unmanned system.

Description

Technical Field

[0001] The present invention relates to a method and system for task allocation of an air-ground collaborative unmanned system based on cooperative game theory. Background Art

[0002] With the rapid development of unmanned system technology, unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) play an increasingly important role in the collaborative operations in military and civilian fields. In complex and dynamic tactical environments, how to real-time evaluate the importance of different unmanned carriers in tasks, especially in air-ground collaborative operations, is the key to ensuring mission success. However, most of the existing evaluation methods lack scientificity and real-time performance, and it is difficult to comprehensively consider multiple factors such as combat capabilities, survivability, tactical coordination, and economic and functional values. Summary of the Invention

[0003] Object of the Invention: To provide a method and system for task allocation of an air-ground collaborative unmanned system based on cooperative game theory, aiming to dynamically allocate tasks and resources by real-time analyzing and evaluating the interdependence and synergy effects among unmanned systems. This method can comprehensively consider the performance parameters, task requirements, environmental factors, and potential collaborative gains of each unmanned system, so as to optimize the task allocation strategy. Through this method, it can be ensured that in the air-ground collaborative combat environment, each unmanned system can be assigned to the task most suitable for its capabilities according to its own advantages and cooperation potential. This not only improves the combat efficiency, but also enhances the adaptability and robustness of the system, providing a scientific and reasonable task allocation scheme for decision-makers to achieve the optimal allocation of combat resources and the maximization of combat effectiveness.

[0004] Technical Solution: To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0005] A method for task allocation of an air-ground collaborative unmanned system based on cooperative game theory, where the unmanned system includes an unmanned aerial vehicle and an unmanned ground vehicle;

[0006] In the air-ground collaborative task environment, each unmanned system is regarded as a participant in the game. Based on cooperative game theory, with the goal of maximizing the overall task benefit, a task allocation scheme for each unmanned system is obtained; where the overall task benefit U total The expression is:

[0007]

[0008] In the formula, and are the utility functions of the unmanned ground vehicle and the unmanned aerial vehicle respectively, a1, a2, a3, θ1, θ2, θ3, β1, and σ1 are all weight coefficients, and R UGV is the task benefit of the unmanned ground vehicle performing the task alone, is the collaborative benefit when the driverless vehicle and the drone cooperate, is the resource consumption when the driverless vehicle executes a task, R UAV is the task benefit when the drone executes a task alone, is the resource consumption when the drone executes a task, R cooperation is the collaborative gain.

[0009] Preferably, based on the set constraints and aiming to maximize the overall task benefit, obtain the task allocation scheme for each unmanned system; where the set constraints include:

[0010] ① Resource constraint

[0011]

[0012] In the formula, is the resource consumption when the driverless vehicle executes a task, is the maximum resource limit of the driverless vehicle, is the resource consumption when the drone executes a task, is the maximum resource limit of the drone;

[0013] ② Task completion time constraint

[0014]

[0015] In the formula, is the total time for the driverless vehicle and the drone to complete the task, T max is the maximum task time limit;

[0016] ③ Success rate constraint

[0017]

[0018] In the formula, and respectively represent the success rates of the driverless vehicle and the drone when executing tasks independently, is the success rate gain in the collaborative mode, P min is the minimum success rate required for the task;

[0019] ④ Speed constraint

[0020]

[0021] Among them, v UGV and v UAV are the speeds of the driverless vehicle and the drone respectively, and are the maximum speeds of the driverless vehicle and the drone respectively;

[0022] ⑤ Load constraint

[0023]

[0024]

[0025] Among them, W UGV and W UAV are the payloads of the unmanned vehicle and the unmanned aerial vehicle respectively, and are the maximum load capacities of the unmanned vehicle and the unmanned aerial vehicle respectively;

[0026] ⑥ Collaboration distance constraint

[0027] D UGV , UAV ≤D max

[0028] Among them, D UGV , UAV is the distance between the unmanned vehicle and the unmanned aerial vehicle, and D max is the maximum collaboration distance.

[0029] Preferably, the Shapley value method and the core element method in cooperative game theory are adopted to obtain the task allocation scheme for each unmanned system.

[0030] Preferably, the task revenue R UGV of the unmanned vehicle executing the task alone is calculated as follows:

[0031]

[0032] Among them, represents the task success rate of the unmanned vehicle executing the task alone, T UGV represents the task completion time of the unmanned vehicle executing the task alone, is the resource consumption when the unmanned vehicle executes the task, and α1, α2, α3 are all weight coefficients.

[0033] Preferably, the task revenue R UAV of the unmanned aerial vehicle executing the task alone is calculated as follows:

[0034]

[0035] Among them, represents the task success rate of the unmanned aerial vehicle executing the task alone, T UAV represents the task completion time of the unmanned aerial vehicle executing the task alone, represents the resource consumption of the unmanned aerial vehicle executing the task, and α1, α2, α3 are all weight coefficients.

[0036] Preferably, the collaboration gain R cooperation and the collaboration revenue The calculation formula is as follows:

[0037] R cooperation = a4·ΔT + a5·ΔP success - a6·ΔC resourcess

[0038]

[0039] Where ΔT is the time savings brought by collaboration, ΔP success is the increase in success rate brought by collaboration, and ΔC resourcess is the reduction in resource consumption brought by collaboration. a4, a5, a6, a7, a8, and a9 are all weight coefficients.

[0040] On the other hand, the present invention also provides an air-ground collaborative unmanned system task allocation system based on the above method, including:

[0041] A data acquisition module for obtaining basic data of the air-ground collaborative task environment, including the task information, resource information, task constraints, success rate, and collaboration benefits of the unmanned system;

[0042] A cooperation benefit model construction module for constructing a cooperation benefit model;

[0043] A cooperation game constraint design module for designing cooperation game constraints;

[0044] A task allocation plan solving module for obtaining a task allocation plan.

[0045] On the other hand, the present invention also provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, and characterized in that when the instructions are executed by a computing device, the computing device executes the above method.

[0046] On the other hand, the present invention also provides an electronic device, including one or more processors, one or more memories, and one or more programs, where the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the above method.

[0047] Beneficial effects: The task allocation method and system for air-ground collaborative unmanned systems based on cooperative game theory proposed by the present invention can effectively solve the problem of how unmanned systems can cooperate efficiently in complex combat environments. Through the application of cooperative game theory, the present invention can accurately evaluate the collaborative potential and task contribution degree among various unmanned systems, so as to achieve the optimal allocation of tasks. This method not only improves the efficiency and success rate of task execution, but also enhances the adaptability and flexibility of unmanned systems in the changing battlefield environment. In addition, the present invention also promotes the rational allocation of resources, ensures the maximum utilization of combat resources, and reduces the combat cost at the same time. Through the present invention, decision-makers can more flexibly respond to battlefield changes, quickly adjust combat strategies, and thus gain an advantage in the fierce modern warfare. Description of the Drawings

[0048] Figure 1 It is the flowchart of the method of the embodiment of the present invention. Detailed Embodiments

[0049] The present invention proposes a task allocation method for air-ground collaborative unmanned systems based on cooperative game theory, aiming to maximize the collaborative benefits of the entire unmanned system group by reasonably allocating tasks. This method analyzes factors such as the combat capabilities, tactical cooperation, survivability, and economic and functional values of unmanned systems, and uses a cooperative game theory model to evaluate the relative contributions and benefit distributions of each unmanned system in collaborative combat tasks. This method first collects real-time data of each unmanned system, and then calculates the utility values of each system under different task allocation schemes through the game theory model, and then determines the optimal task allocation scheme. Through this method, it can be ensured that each unmanned system can exert its maximum efficiency in the task, while ensuring the collaborative efficiency and task success rate of the entire system. This method has high adaptability and flexibility, can adapt to the changing battlefield environment and task requirements, and provides an effective task allocation strategy for the collaborative combat of unmanned systems.

[0050] As Figure 1 shown, a task allocation method for air-ground collaborative unmanned systems based on cooperative game theory of the present invention includes the following steps:

[0051] (1) Basic data collection. In the air-ground collaborative task environment, the collected data includes the following:

[0052] · Unmanned ground vehicle (UGV) task information: including task type, task objective, task location (unit: longitude and latitude, acquisition method: through the task planning system or preset task library), maximum load (unit: kg, acquisition method: estimated through the UGV specifications or task requirements), and task required time (unit: hours, acquisition method: through historical task data or real-time estimation model).

[0053] · Unmanned Aerial Vehicle (UAV) mission information: including mission type, mission objective, mission location (unit: longitude and latitude, acquisition method: through mission planning system or preset mission library), flight time (unit: hours, acquisition method: through flight control system or model estimation), flight altitude (unit: meters, acquisition method:

[0054] set through flight parameters or adjusted in real time).

[0055] · Unmanned Ground Vehicle (UGV) and Unmanned Aerial Vehicle (UAV) resource information: including remaining battery power (unit: %, acquisition method: real-time monitoring through sensors), energy consumption rate (unit: W, acquisition method: obtained through hardware sensors or system models), remaining fuel (unit: L, acquisition method: obtained in real time through on-vehicle fuel sensors).

[0056] · Mission collaboration constraints: including maximum collaboration distance (unit: meters, acquisition method: obtained through mission settings or previous operation data), mission time limit (unit: hours, acquisition method: set according to mission requirements or environmental restrictions).

[0057] · Success rate model: including initial success rate (unit: %, acquisition method: obtained through historical mission data analysis or simulation results), collaboration gain model (unit: %, acquisition method: obtained through historical data analysis or simulation models).

[0058] · Collaboration benefit parameters: including the comprehensive benefit brought by mission collaboration (unit: dimensionless, acquisition method: obtained through collaboration benefit analysis model or simulation analysis).

[0059] · Mission constraints: including maximum mission completion time (unit: hours, acquisition method: provided by mission requirements or calculated and estimated), mission priority (unit: dimensionless, acquisition method: set through mission library or mission assignment system).

[0060] (2) Construction of game model framework

[0061] In the collaborative mission of unmanned ground vehicle and unmanned aerial vehicle, each system acts as a participant in the game and achieves the maximum benefit of the mission through cooperation. The goal of the game is to optimize the overall benefit of the system through cooperation, rather than simply optimizing the benefit of each unmanned system.

[0062] · Participants: Unmanned Ground Vehicle (UGV) and Unmanned Aerial Vehicle (UAV). Each system makes strategy choices based on its own mission execution capabilities, available resources, etc.

[0063] · Strategy set: The strategy set of each unmanned system can be choices of mission assignment, choices of collaboration methods (such as providing support, sharing data, coordinating with each other, etc.).

[0064] · Utility function: The utility function represents the payoff obtained by each participant after choosing a strategy, usually reflecting the gains brought by collaboration, such as the reduction of task completion time, resource savings, and improvement of task completion rate, etc.

[0065] (3) Construction of the cooperation payoff model

[0066] When the unmanned ground vehicle (UGV) and the unmanned aerial vehicle (UAV) collaborate, the payoff of the task can be divided into the following parts:

[0067] 1. The payoff R1 completed only by the unmanned ground vehicle UGW

[0068] The payoff when the unmanned ground vehicle executes the task independently is mainly related to factors such as task completion time, success rate, and resource consumption. Its calculation formula is as follows:

[0069]

[0070] Among them:

[0071] · represents the task success rate;

[0072] · T UGV represents the task completion time;

[0073] · represents the resource consumption;

[0074] · α1, α2, α3 are weight coefficients, indicating the influence of different factors on the payoff.

[0075] 2. The payoff R2 completed only by the unmanned aerial vehicle UAV

[0076] Similarly, the calculation formula for the payoff when the unmanned aerial vehicle completes the task independently is:

[0077]

[0078] Among them:

[0079] · represents the task success rate;

[0080] · T UAV represents the task completion time;

[0081] · represents the resource consumption;

[0082] · α1, α2, β3 are weight coefficients, indicating the influence of different factors on the payoff.

[0083] 3. The additional payoff R3 brought by collaboration cooperation

[0084] The benefits brought by collaboration are mainly reflected in the following aspects:

[0085] · Time savings for tasks: When the unmanned vehicle and the unmanned aerial vehicle collaborate, the task completion time is reduced;

[0086] · Improvement in success rate: Collaboration helps to improve the success rate of tasks, especially in complex tasks or environments;

[0087] · Reduction in resource consumption: Collaboration can reduce resource consumption through reasonable division of labor.

[0088] The calculation of collaboration gain can be through the following formula:

[0089] R cooperation = a4·ΔT + a5·ΔP success - a6·ΔC resourcess

[0090] Where:

[0091] · ΔT is the time savings brought by collaboration;

[0092] · ΔP success is the improvement in success rate brought by collaboration;

[0093] · ΔC resourcess is the reduction in resource consumption brought by collaboration;

[0094] · a4, a5, a6 are the corresponding weight coefficients.

[0095] 4. Collaboration benefits

[0096] The collaboration benefits in the collaboration mode can be expressed as:

[0097]

[0098] (4) Utility function design

[0099] In a cooperative game, the role of the utility function is to quantify the preferences and interests of each participant (unmanned vehicle and unmanned aerial vehicle) in task allocation. Through the utility function, each participant selects the optimal strategy based on its own interest maximization. In this task allocation model, the utility function will depend on factors such as task completion benefits, collaboration gain, and resource consumption.

[0100] The utility functions of the unmanned vehicle and the unmanned aerial vehicle should reflect their benefits and consumptions in task execution. The utility functions and are calculated as follows:

[0101]

[0102] Wherein:

[0103] ·R UGV is the revenue of the unmanned vehicle executing the task alone (refer to the aforementioned revenue model);

[0104] ·R UAV is the revenue of the unmanned aerial vehicle executing the task alone (refer to the aforementioned revenue model);

[0105] · is the revenue when the unmanned vehicle and the unmanned aerial vehicle cooperate;

[0106] · is the resource consumption of the unmanned vehicle when executing the task;

[0107] · is the resource consumption of the unmanned aerial vehicle when executing the task;

[0108] ·R cooperation is the cooperation gain (such as time saving, success rate improvement, resource consumption reduction, etc.);

[0109] ·a1, a2, a3, θ1, θ2, θ3 are weight coefficients, representing the relative importance of task revenue, cooperation revenue and resource consumption;

[0110] ·β1, σ1 are weight coefficients of the cooperation gain, representing the contribution of cooperation to the utility of the unmanned vehicle and the unmanned aerial vehicle.

[0111] Calculate the utility value of each unmanned system for all tasks by the above utility function, and obtain a utility matrix U task , where U i,j represents the utility value of assigning task j to unmanned system i, and the unmanned system refers to a single unmanned aerial vehicle or unmanned vehicle:

[0112]

[0113] where n is the number of unmanned systems and m is the number of tasks.

[0114] In the cooperative game, the goal is to maximize the interests of each participant according to its own utility function. By solving the Nash equilibrium or other cooperative game optimization methods, each system can select the optimal strategy and finally achieve the optimal allocation of tasks. The ultimate goal of the utility function is to obtain the output matrix through the optimization algorithm:

[0115]

[0116] where T i,j represents whether to assign task j to unmanned system i:

[0117]

[0118] Maximize the utility function U of the matrix total to its maximum value:

[0119]

[0120] (5) Cooperative game constraint design

[0121] 1. Resource constraints

[0122] Both unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) are restricted by resources when performing tasks. To ensure that tasks can be executed under actual conditions, resource constraints must be set to avoid exceeding the physical limits of the system. For example, the battery power, fuel, payload capacity, etc. of UGVs and UAVs are key resources.

[0123] · UGV resource constraint:

[0124]

[0125] where is the resource consumption of the UGV when performing the task, is the maximum resource limit of the UGV.

[0126] · UAV resource constraint:

[0127]

[0128] where is the resource consumption of the UAV when performing the task, is the maximum resource limit of the UAV.

[0129] 2. Task completion time constraint

[0130] In a collaborative mode, the completion time of the task should not exceed the predetermined maximum time limit. Therefore, the total completion time of the task needs to meet the given time limit. This can be achieved by calculating the collaborative task completion time to ensure that the task is completed on time.

[0131] · Total task completion time constraint:

[0132]

[0133] where is the total time for the UGV and UAV to complete the task collaboratively, and T max is the maximum task time limit.

[0134] 3. Success rate constraint

[0135] The success rate of a task directly affects the completion effect of the task. Generally, the success rate of a task should reach a certain minimum standard to ensure the maintainability of the task. In the collaborative mode, the success rate usually increases, so a minimum threshold for the success rate should be set.

[0136] · Success rate constraint:

[0137]

[0138] Among them, and respectively represent the success rates of the unmanned vehicle and the unmanned aerial vehicle when performing tasks independently, is the success rate gain in the collaborative mode, and P min is the minimum success rate required for the task.

[0139] 4. Collaboration distance constraint

[0140] The collaboration between the unmanned vehicle and the unmanned aerial vehicle needs to be maintained within a certain distance range to ensure the effectiveness and accuracy of the collaboration. Too far a distance may lead to a decline in the collaboration effect. Therefore, an upper limit for the collaboration distance needs to be set.

[0141] · Collaboration distance constraint:

[0142] D UGV 、 UAV ≤D max

[0143] Among them, D UGV 、 UAV is the distance between the unmanned vehicle and the unmanned aerial vehicle, and D max is the maximum collaboration distance.

[0144] 5. Physical constraints

[0145] Physical constraints refer to the limitations related to the physical characteristics of the unmanned vehicle and the unmanned aerial vehicle, such as speed, load capacity, flight range, etc. These constraints ensure that the task assignment scheme is feasible under actual physical conditions.

[0146] · Speed constraint:

[0147]

[0148] Among them, v UGV and v UAV respectively represent the speeds of the unmanned vehicle and the unmanned aerial vehicle, and are their maximum speeds.

[0149] · Load constraint:

[0150]

[0151] Among them, W UGV and W UAV are the payloads of the unmanned vehicle and the unmanned aerial vehicle respectively, and are their maximum load capacities.

[0152] 6. Other Constraints

[0153] In practical applications, other types of constraints may also need to be considered, such as environmental changes, task priorities, obstacle avoidance, etc. These constraints are designed according to the requirements of specific task scenarios.

[0154] (6) Cooperative Game Optimization Solving

[0155] Based on the utility functions of the unmanned aerial vehicle and the unmanned vehicle and the constraint conditions of task allocation, the Shapley value method and the core element method in cooperative game theory are used to solve the optimal task allocation scheme. By analyzing the cooperation benefits among various unmanned systems, the contribution of each system in cooperation is determined, and the cooperation mode between the unmanned vehicle and the unmanned aerial vehicle is optimized. Thus, while considering resource consumption, time saving, and success rate improvement, the overall task benefit is maximized, and finally the task allocation matrix is obtained:

[0156]

[0157] The present invention also provides a task allocation system for an air-ground collaborative unmanned system, and the system includes:

[0158] A data acquisition module, configured to obtain the basic data of the air-ground collaborative task environment, including the task information, resource information, task constraints, success rate, and cooperation benefits of the unmanned system;

[0159] A cooperation benefit model construction module, configured to construct a cooperation benefit model;

[0160] A cooperative game constraint design module, configured to design cooperative game constraints;

[0161] A task allocation scheme solving module, configured to obtain a task allocation scheme.

[0162] The technical solution of the above-mentioned task allocation system for the air-ground collaborative unmanned system is similar to the technical solution of the foregoing task allocation method for the air-ground collaborative unmanned system, and will not be elaborated here.

[0163] Based on the same technical solution, the present invention also provides a computer-readable storage medium storing one or more programs, and the one or more programs include instructions, and are characterized in that when the instructions are executed by a computing device, the computing device is caused to execute the task allocation method for the air-ground collaborative unmanned system as described above.

[0164] Based on the same technical solution, the present invention also provides an electronic system, including one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the air-ground collaborative unmanned system task allocation method as described above.

[0165] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0166] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0167] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0169] To more clearly demonstrate the practical application of the method of the present invention, a specific case is provided below for specific elaboration.

[0170] Case illustration: Suppose in a certain air-ground collaborative operation mission, we have two unmanned carriers: an unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV). They are performing a joint mission and now need to allocate tasks.

[0171] The following will adopt a task allocation method for an air-ground collaborative unmanned system based on cooperative game theory proposed by the present invention:

[0172] (1) Basic data collection

[0173] · Unmanned ground vehicle (UGV) task information:

[0174] Task success rate: Task completion time: T UGV = 60s; Resource consumption:

[0175]

[0176] · Unmanned aerial vehicle (UAV) task information:

[0177] Task success rate: Task completion time: T UAV = 40s; Resource consumption:

[0178] Benefit when the unmanned ground vehicle and the unmanned aerial vehicle cooperate:

[0179] · Unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV) resource information:

[0180] Time savings brought by cooperation: ΔT = 20s; Success rate improvement brought by cooperation: ΔP success = 0.2;

[0181] Resource consumption reduction brought by cooperation: ΔC resourcess = 30; Total resource consumption:

[0182] · Task constraints:

[0183] Maximum resource limit of the unmanned ground vehicle Maximum resource limit of the unmanned ground vehicle: Maximum task time limit: T max = 300s; Minimum success rate required for the task: P min = 0.99; Maximum cooperation distance:

[0184] D max = 100; Maximum speed: and Maximum load: and

[0185] (2) Construction of the game model framework

[0186] In the collaborative tasks of unmanned vehicles and drones, each system acts as a participant in the game and achieves the maximum benefit of the task through cooperation. The goal of the game is to optimize the overall benefit of the system through cooperation, rather than simply optimizing the benefit of each unmanned system.

[0187] · Participants: Unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV). Each system makes strategy choices based on its own task execution capabilities, available resources, etc.

[0188] · Strategy set: The strategy set of each unmanned system can be choices of task allocation, choices of cooperation methods (such as providing support, sharing data, coordinating with each other, etc.).

[0189] · Utility function: The utility function represents the benefit obtained by each participant after choosing a strategy, usually reflecting the gain brought by cooperation, such as shortening the task completion time, saving resources, improving the task completion degree, etc.

[0190] (3) Construction of the cooperation benefit model:

[0191] When the unmanned ground vehicle (UGV) and the unmanned aerial vehicle (UAV) cooperate, the comprehensive benefit of the task can be divided into the following parts:

[0192] · Benefit R completed only by the unmanned ground vehicle UGV

[0193] It is set that in this case, the values of the weight coefficients are:

[0194] α1 = α2 = α3 = 1.0.

[0195] Substituting into the formula, we can get:

[0196]

[0197] · Benefit R completed only by the unmanned aerial vehicle UAV

[0198] It is set that in this case, the values of the weight coefficients are:

[0199] α1 = α2 = α3 = 1.0.

[0200] Similarly, the benefit calculation formula when the unmanned aerial vehicle completes the task independently is:

[0201]

[0202] · Additional benefit R brought by collaboration cooperation

[0203] It is set that in this case, the values of the weight coefficients are as follows:

[0204] α4 = α5 = α6 = α7 = α8 = α9 = 1.0.

[0205] The calculation of the collaboration gain can be through the following formula:

[0206] R cooperation = a4·ΔT + a5·ΔP success - a6·ΔC resourcess

[0207] = 1.0·20 - 1.0·0.2 - 1.0·30 = -10.2.

[0208] · Collaboration benefit

[0209] The collaboration benefit in the collaboration mode can be expressed as:

[0210]

[0211] (4) Utility function calculation:

[0212] It is set that in this case, the values of the weight coefficients are as follows:

[0213] α1 = α2 = β3 = β1 = 1.0.

[0214] The utility function of the unmanned vehicle should reflect its benefits and costs in task execution. The utility function is calculated as follows:

[0215]

[0216] Similarly, it can be obtained that:

[0217] Repeatedly obtain the utility matrix:

[0218]

[0219] In a cooperative game, the goal is to maximize the interests of each participant according to its own utility function. By solving the Nash equilibrium or other cooperative game optimization methods, each system can select the optimal strategy and ultimately achieve the optimal allocation of tasks. The ultimate goal of the utility function is to make U total maximum:

[0220]

[0221] (5) Construction of cooperative game constraints:

[0222] 1. Resource constraints

[0223] · Resource constraints of driverless vehicles:

[0224]

[0225] · Resource constraints of drones:

[0226]

[0227] 2. Task completion time constraints

[0228] · Total task completion time constraint:

[0229]

[0230] Among them, is the total time for the driverless vehicle and the drone to complete the task in cooperation.

[0231] 3. Success rate constraints

[0232]

[0233] Among them, and respectively represent the success rates of the driverless vehicle and the drone when performing tasks independently,

[0234] is the success rate gain in the cooperation mode.

[0235] 4. Collaboration distance constraints

[0236] D UGV 、 UAV ≤D max =100

[0237] Among them, D UGV 、 UAV is the distance between the driverless vehicle and the drone.

[0238] 5. Physical constraints

[0239] · Speed constraints:

[0240]

[0241] Among them, v UGV and v UAV are the speeds of the driverless vehicle and the drone respectively.

[0242] · Load capacity constraints:

[0243]

[0244] Among them, W UGV and W UAV are the payloads of the unmanned vehicle and the unmanned aerial vehicle respectively.

[0245] 6. Other Constraints

[0246] In practical applications, other types of constraints may also need to be considered, such as environmental changes, task priorities, obstacle avoidance, etc. These constraints are designed according to the requirements of specific task scenarios.

[0247] (6) Cooperative Game Optimization Solving:

[0248] The method of the cooperative game optimization solving is as follows: Based on the utility functions of the unmanned aerial vehicle and the unmanned vehicle and the constraint conditions of the task allocation, the Shapley value method and the core element method in the cooperative game theory are used to solve the optimal task allocation scheme. By analyzing the cooperation benefits among various unmanned systems, determining the contributions of each system in the cooperation, and optimizing the cooperation mode between the unmanned vehicle and the unmanned aerial vehicle, while considering resource consumption, time saving, and success rate improvement, the overall task benefit is maximized, and finally the task allocation matrix is obtained:

[0249]

[0250] Obviously, the above embodiments are only examples clearly described and not limitations on the usage methods. For those skilled in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to list all the usage methods here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for task allocation of air-ground cooperative unmanned systems based on cooperative game theory, characterized in that, The unmanned system includes an unmanned aerial vehicle and an unmanned vehicle; In the air-ground collaborative task environment, each unmanned system is regarded as a participant in the game in the task allocation method. Based on the cooperative game theory, with the goal of maximizing the cooperative benefit, the task allocation scheme for each unmanned system is obtained; Among them, the cooperation benefit U total has the following expression: Wherein, and are the utility functions of the unmanned vehicle and the unmanned aerial vehicle respectively. a1, a2, a3, θ1, θ2, θ3, β1 and σ1 are all weight coefficients. R UGV is the task revenue of the unmanned vehicle performing the task alone, is the collaborative revenue when the unmanned vehicle and the unmanned aerial vehicle cooperate, is the resource consumption when the unmanned vehicle performs the task. R UAV is the task revenue of the unmanned aerial vehicle performing the task alone, is the resource consumption when the unmanned aerial vehicle performs the task. R cooperation is the collaborative gain.

2. The method according to claim 1, wherein Based on the cooperative game constraints, with the goal of maximizing the overall task benefit, the task allocation scheme for each unmanned system is obtained; Among them, the cooperative game constraints include: ① Resource constraints In the formula, is the resource consumption when the unmanned vehicle performs tasks, is the maximum resource limit of the unmanned vehicle, is the resource consumption when the unmanned aerial vehicle performs tasks, is the maximum resource limit of the unmanned aerial vehicle; ② Task completion time constraints In the formula, is the total time for the unmanned vehicle and the unmanned aerial vehicle to complete the task collaboratively, and T max is the maximum task time limit; ③ Success rate constraints In the formula, and respectively represent the success rates of the unmanned vehicle and the unmanned aerial vehicle when performing tasks independently, is the success rate gain in the collaborative mode, and P min is the minimum success rate required for the task; ④ Speed constraints Among them, v UGV and v UAV are the speeds of the unmanned vehicle and the unmanned aerial vehicle respectively, and are the maximum speeds of the unmanned vehicle and the unmanned aerial vehicle respectively; ⑤ Payload constraints Among them, W UGV and W UAV are the payloads of the unmanned vehicle and the unmanned aerial vehicle respectively, and are the maximum load capacities of the unmanned vehicle and the unmanned aerial vehicle respectively; ⑥ Collaboration distance constraints D UGV 、 UAV ≤ D max Among them, D UGV , UAV is the distance between the driverless vehicle and the drone, and D max is the maximum cooperation distance.

3. The method according to claim 1 or 2, characterized in that, The Shapley value method and the core element method in the cooperative game theory are used to obtain the task allocation scheme for each unmanned system.

4. The method according to claim 1, wherein The mission revenue R of the driverless vehicle executing tasks alone UGV is calculated as follows: Among them, represents the task success rate of the unmanned vehicle executing tasks alone, T UGV represents the task completion time of the unmanned vehicle executing tasks, is the resource consumption when the unmanned vehicle executes tasks, and α1, α2, and α3 are all weight coefficients.

5. The method according to claim 1, characterized in that, The mission benefit R of the UAV performing tasks alone UAV The calculation formula is as follows: Among them, represents the mission success rate of the UAV performing the mission alone, T UAV represents the mission completion time of the UAV performing the mission, represents the resource consumption of the UAV performing the mission, and α1, α2, and α3 are all weight coefficients.

6. The method according to claim 1, wherein Cooperative gain R cooperation The calculation formula is as follows: R cooperation = a4·ΔT + a5·ΔP success - a6·ΔC resourcess Among them, ΔT is the time saving brought by collaboration, and ΔP success is the success rate improvement brought by collaboration, and ΔC resourcess is the resource consumption reduction brought by collaboration. a4, a5, and a6 are all weight coefficients.

7. The method according to claim 1, characterized in that, Collaborative benefits The calculation formula is as follows: where, ΔT is the time saving brought by collaboration, and ΔP success is the success rate improvement brought by collaboration, T UGV represents the task completion time of the unmanned vehicle executing the task, T UAV represents the task completion time of the unmanned aerial vehicle executing the task, is the resource consumption when the unmanned vehicle executes the task, represents the resource consumption of the unmanned aerial vehicle executing the task, represents the task success rate of the unmanned vehicle executing the task alone, represents the task success rate of the unmanned aerial vehicle executing the task alone, and ΔC resourcess is the reduction in resource consumption brought by collaboration. a7, a8, and a9 are all weight coefficients.

8. An air-ground collaborative unmanned system mission allocation system based on the method according to any one of claims 1 to 7, characterized in that, It includes: A data acquisition module, which is used to obtain the basic data of the air-ground collaborative task environment, including the task information, resource information, task constraints, success rate, and collaboration benefit of the unmanned system; A cooperative benefit model construction module, which is used to construct a cooperative benefit model; A cooperative game constraint design module, which is used to design cooperative game constraints; A task allocation scheme solving module, which is used to obtain a task allocation scheme.

9. A computer-readable storage medium storing one or more programs, the one or more programs including instructions, characterized in that, When executed by a computing device, the instructions cause the computing device to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors, one or more memories, and one or more programs, wherein one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to any one of claims 1 to 7.

Images