Unmanned platform autonomous decision-making capability assessment method and system, electronic equipment and storage medium

Abstract

The invention provides an unmanned platform autonomous decision-making ability evaluation method and system, electronic equipment and a storage medium, and relates to the field of artificial intelligence, and the method comprises the steps: designing an evaluation index of the unmanned platform autonomous decision-making ability; according to the evaluation index, establishing a target table strategy capability function model to obtain an attribute function; performing normalization preprocessing on the attribute function; constructing an autonomous level decision matrix according to the normalized attribute function; constructing a priority function according to the autonomous level decision matrix; and according to the priority function, comparing the priority ranking to obtain the ranking of the autonomous levels. According to the method, task-oriented autonomous intelligent decision-making capability evaluation can be completed in a typical complex environment, and the target of effectively improving the task completion degree of the unmanned platform is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence, and particularly relates to a method, a system, an electronic device, and a storage medium for evaluating the autonomous decision-making ability of an unmanned platform. Background Art

[0002] At present, an unmanned platform is an unmanned mobile platform that completes maneuvers, assists, or replaces humans to complete special tasks under controlled or autonomous conditions. In many cases, the unmanned platform has to complete tasks that are not clearly arranged in advance in an unknown environment with unclear situations. Due to a series of restrictive factors such as the unknown nature of the complex environment, low autonomous decision-making ability, and lack of efficient hardware support conditions and software tools, the evaluation methods for the decision-making ability of the unmanned platform are single, and there is a need to break through the dynamic real-time solution of the autonomous decision-making ability.

[0003] Therefore, how to provide a method, a system, an electronic device, and a storage medium for evaluating the autonomous decision-making ability of an unmanned platform has become a technical problem that needs to be solved urgently in this field. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, a system, an electronic device, and a storage medium for evaluating the autonomous decision-making ability of an unmanned platform.

[0005] According to the first aspect of the present invention, there is provided a method for evaluating the autonomous decision-making ability of an unmanned platform, including,

[0006] Step S1: Design evaluation indicators for the autonomous decision-making ability of the unmanned platform;

[0007] Step S2: Establish a target decision-making ability function model according to the evaluation indicators to obtain an attribute function;

[0008] Step S3: Perform normalization preprocessing on the attribute function;

[0009] Step S4: Construct an autonomous level decision matrix according to the normalized attribute function;

[0010] Step S5: Construct a priority function according to the autonomous level decision matrix;

[0011] Step S6: Compare the priority rankings according to the priority function to obtain the ranking of the autonomous levels.

[0012] Preferably, in the step S1, the evaluation indicators include an environmental perception indicator, a task planning indicator, a platform status indicator, and a user status indicator;

[0013] The environmental perception indicators include geographical environment indicators and situation environment indicators. Among them, the geographical environment indicators include the road detection and tracking ability level, the dynamic collision avoidance ability level, and the meteorological perception ability level; the situation environment indicators include the battlefield environment threat level, the number of our clusters, and the number of other clusters;

[0014] The mission planning indicators include mission planning indicators and action planning indicators. Among them, the mission planning indicators include the mission level, the mission type, the mission planning duration level, and the number of mission participants; the action planning indicators include the mission path planning ability level, the obstacle avoidance planning ability level, and the parking planning ability level;

[0015] The platform status indicators include the platform ability level and the platform real-time status indicators. Among them, the platform ability level includes the platform tonnage level, the platform load level, and the platform cooperation management level; the platform real-time status indicators include the loaded weapon level, the number of loaded weapons, and the damage status level;

[0016] The user status indicators include the user qualification level indicators and the user individual status indicators. Among them, the user qualification level indicators include the user skill level, the historical evaluation level for use, and the user operation proficiency;

[0017] The user individual status indicators include the user interaction duration and the user mental state level.

[0018] Preferably, in the step S2, the target decision-making ability function model is:

[0019] F(l i ) = F(f 1 (l i ), f 2 (l i ),..., f m (l i )) (2)

[0020] where l i ∈L, L = {l 1 , l 2 , l 3 , l 4 , l 5},

[0021] f 1 (l), f 2 (l),..., f m (l) are 24 attribute functions corresponding to the evaluation index set, that is, m = 24;

[0022] l i is the corresponding feasible autonomous level of the unmanned ground platform, that is, i = 5;

[0023] w j is the weight of the evaluation index, and the sum of the weights is 1, which can be obtained through the expert analytic hierarchy process, that is, j = 24.

[0024] When the user operator has different preferences, the personality tending to be risk - type or conservative can be reflected by adjusting the weights.

[0025] Preferably, in the step S3, the normalization pre - processing method is as follows:

[0026] Among them, the environmental perception index and the task planning index are extremely large - type indexes, and the normalization formula is as follows:

[0027]

[0028] Among them, the platform status index and the user status index are extremely small - type indexes, and the normalization formula is as follows:

[0029]

[0030] Among them, f ij (l) is the attribute function; f ij (l) is the expected value of the attribute function, is the maximum value, is the minimum value.

[0031] Preferably, in the step S4, the autonomous level decision matrix is constructed as follows:

[0032] d j (l i , l j ) = f j (l i ) - f j (l j ) (5);

[0033] D 5×24 = {d ij} (6);

[0034] Among them, d ij is the j - th attribute value of the autonomous level i minus the j - th attribute value of the autonomous level j, indicating the degree of achievement of the j - th attribute value of the autonomous level l j measured by the attribute function f i ; D 5×24 represents the decision matrix with an autonomous level of 5 and 24 attribute quantities composed of d ij , where the R ij is f ij (l) in the autonomous level decision matrix.

[0035] Preferably, in the step S5, in multi-attribute decision-making, the priority degree between each pair of autonomous levels is calculated by a defined priority function, and the priority function is as follows:

[0036] If d ij ≤d kj , its value is 0; otherwise it is d j (l i , l j ), that is:

[0037]

[0038] where P(l i , l k ) is the priority degree of the attribute value.

[0039] Preferably, in the step S6, according to the priority function, the comparison sorting index is:

[0040]

[0041] For the index l i , l j ∈L, the weight values of individual attributes are w j , j = 1, 2,..., 24, ∏(l i , l k ) represents the directed attribute value of the autonomous level l i , l k from l i pointing to l k ;

[0042] Define the net inflow value φ(l i ) of the autonomous level i as follows:

[0043]

[0044] By comparing the net flow magnitudes of each autonomous level, the level sorting relationship can be determined; if φ(l i ) > φ(l k ), the level of l i is higher than that of l k ; if φ(l i ) < φ(l k ), the level of l i is lower than that of l k , thus completing the sorting of the feasible autonomous levels.

[0045] According to the second aspect of the present invention, there is provided an unmanned platform autonomous decision-making ability evaluation system, including,

[0046] A first processing module, configured to design evaluation indicators for the unmanned platform autonomous decision-making ability;

[0047] A second processing module, configured to establish a target decision-making ability function model according to evaluation metrics and obtain an attribute function;

[0048] A third processing module, configured to perform normalization preprocessing on the attribute function;

[0049] A fourth processing module, configured to construct an autonomous level decision matrix according to the normalized attribute function;

[0050] A fifth processing module, configured to construct a priority function according to the autonomous level decision matrix;

[0051] A sixth processing module, configured to compare the priority rankings according to the priority function to obtain the ranking of the autonomous levels.

[0052] For the system according to the second aspect of the present invention, the first processing module is specifically configured that the evaluation metrics include environmental perception metrics, task planning metrics, platform status metrics, and user status metrics;

[0053] The environmental perception metrics include geographical environment metrics and situation environment metrics. Among them, the geographical environment metrics include road detection and tracking ability level, dynamic collision avoidance ability level, and meteorological perception ability level; the situation environment metrics include battlefield environment threat level, the number of our clusters, and the number of other clusters;

[0054] The task planning metrics include task planning metrics and action planning metrics. Among them, the task planning metrics include task level, task type, task planning duration level, and the number of task participants; the action planning metrics include task path planning ability level, obstacle avoidance planning ability level, and parking planning ability level;

[0055] The platform status metrics include platform ability level metrics and platform real-time status metrics. Among them, the platform ability level metrics include platform tonnage level, platform load level, and platform collaboration management level; the platform real-time status metrics include loaded weapon level, the number of loaded weapons, and damage status level;

[0056] The user status metrics include user qualification level metrics and user individual status metrics. Among them, the user qualification level metrics include user skill level, historical evaluation level for users, and user operation proficiency;

[0057] The user individual status metrics include user interaction duration and user mental state level.

[0058] For the system according to the second aspect of the present invention, the second processing module is specifically configured that the target decision-making ability function model is:

[0059] F(li ) = F(f 1 (l j ), f 2 (l i ),..., f m (l i )) (2)

[0060] Among them, l i ∈L, L = {l 1 , l 2 , l 3 , l 4 , l 5},

[0061] f 1 (l), f 2 (l), …, f m (l) are 24 attribute functions of the corresponding evaluation index set, that is, m = 24;

[0062] l i corresponds to the feasible autonomous level of the unmanned ground platform, that is, i = 5;

[0063] w j is the evaluation index weight, and the sum of the weights is 1, which can be obtained by the expert analytic hierarchy process, that is, j = 24.

[0064] When the user operator has different preferences, their personality tending to be risk - seeking or conservative can be reflected by adjusting the weights.

[0065] According to the system of the second aspect of the present invention, the third processing module is specifically configured as follows for the normalization pre - processing:

[0066] Among them, the environmental perception index and the task planning index are extremely large - type indexes, and the normalization formula is as follows:

[0067]

[0068] Among them, the platform status index and the user status index are extremely small - type indexes, and the normalization formula is as follows:

[0069]

[0070] Among them, f ij (l) is the attribute function; f ij (l) is the expected value of the attribute function, is the maximum value, is the minimum value.

[0071] According to the system of the second aspect of the present invention, the fourth processing module is specifically configured to construct an autonomous level decision matrix as follows:

[0072] d j (l i ,l j ) = f j (l i ) - f j (l j ) (5);

[0073] D 5×24 = {d ij}} (6);

[0074] Wherein, d ij is the j - attribute value of autonomy level i minus the j - attribute value of autonomy level j, representing the degree of achievement of the j - th attribute value for measuring autonomy level l j by the attribute function f i ; D 5×24 represents the decision - making matrix with autonomy level 5 and 24 attribute quantities composed of d ij , where R is obtained by formulas (3) and (4) ij is f ij (l) in the autonomy - level decision - making matrix.

[0075] According to the system of the second aspect of the present invention, the fifth processing module is specifically configured to calculate the priority degree between each pair of autonomy levels in multi - attribute decision - making through a defined priority function. The priority function is as follows:

[0076] If d ij ≤d kj , its value is 0; otherwise it is d j (l i , l j ), that is:

[0077]

[0078] Where P(l i , l k ) is the priority degree of the attribute value.

[0079] According to the system of the second aspect of the present invention, the sixth processing module is specifically configured to compare and sort the index according to the priority function as:

[0080]

[0081] For index l i , l j ∈L, the weight values of individual attributes are respectively w j , j = 1, 2,..., 24, ∏(l i , l k ) represents autonomy level li , l k , which is directed from l i to l k with a directed attribute value;

[0082] Define the net inflow value φ(l i ) of the autonomous level i as follows:

[0083]

[0084] By comparing the net flows of each autonomous level, the level sorting relationship can be determined; if φ(l i ) > φ(l k ), l i is at a higher level than l k ; if φ(l i ) < φ(l k ), l i is at a lower level than l k ), thus completing the sorting of the feasible autonomous levels.

[0085] The third aspect of the present invention discloses an electronic device. The electronic device includes a memory and a processor. When the processor executes the computer program stored in the memory, the steps in any one of the methods for evaluating the autonomous decision-making ability of an unmanned platform in the first aspect of the present disclosure are implemented.

[0086] The fourth aspect of the present invention discloses a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the steps in any one of the methods for evaluating the autonomous decision-making ability of an unmanned platform in the first aspect of the present disclosure are implemented.

[0087] As can be seen from the above solutions, the embodiments of the present invention provide a method, a system, an electronic device, and a storage medium for evaluating the autonomous decision-making ability of an unmanned platform, having the following beneficial effects:

[0088] In response to the requirements of an unmanned platform for performing tasks in a complex environment, considering the current situation of the unmanned platform such as complex environment, limited continuous operation time, and low fully autonomous intelligent decision-making and control ability, the present application proposes an algorithm for evaluating the autonomous decision-making ability of an unmanned platform for high-efficiency human-machine collaboration. This algorithm can complete the evaluation of the autonomous intelligent decision-making ability for tasks in a typical complex environment, achieving the goal of effectively improving the task completion rate of the unmanned platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 is a flowchart of a method for evaluating the autonomous decision-making ability of an unmanned platform according to an embodiment;

[0090] Figure 2Schematic diagram of evaluation indicators in an autonomous decision-making ability evaluation method for an unmanned platform provided according to an embodiment;

[0091] Figure 3 Flowchart of an autonomous decision-making ability evaluation method for an unmanned platform provided in Embodiment 2;

[0092] Figure 4 Structural diagram of a system for an autonomous decision-making ability evaluation method for an unmanned platform according to an embodiment of the present invention;

[0093] Figure 5 Structural diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0094] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0095] Embodiment 1:

[0096] According to the first aspect of the present invention, the present invention discloses an autonomous decision-making ability evaluation method for an unmanned platform. Figure 1 As a flowchart of an autonomous decision-making ability evaluation method for an unmanned platform according to an embodiment of the present invention, as Figure 1 shown, the method includes:

[0097] Step S1, designing evaluation indicators for the autonomous decision-making ability of the unmanned platform;

[0098] As Figure 2 shown, in the step S1, the evaluation indicators include environmental perception indicators, task planning indicators, platform status indicators, and user status indicators;

[0099] The environmental perception indicators include geographical environment indicators and situation environment indicators. Among them, the geographical environment indicators include road detection and tracking ability level, dynamic collision avoidance ability level, and meteorological perception ability level; the situation environment indicators include battlefield environment threat level, the number of our own clusters, and the number of other clusters;

[0100] The task planning indicators include mission planning indicators and action planning indicators. Among them, the mission planning indicators include mission level, mission type, mission planning duration level, and the number of mission participants; the action planning indicators include mission path planning ability level, obstacle avoidance planning ability level, and parking planning ability level;

[0101] The platform status indicators include the platform capability level and indicators and the platform real-time status indicators. Among them, the platform capability level includes the platform tonnage level, the platform load level, and the platform cooperation management level; the platform real-time status indicators include the loaded weapon level, the number of loaded weapons, and the damage status level;

[0102] The user status indicators include the user qualification level indicators and the user individual status indicators. Among them, the user qualification level indicators include the user skill level, the historical evaluation level for users, and the user operation proficiency;

[0103] The user individual status indicators include the user interaction duration and the user mental state level.

[0104] Step S2: According to the evaluation indicators, establish a target decision-making ability function model to obtain the attribute functions;

[0105] In the step S2, the target decision-making ability function model is:

[0106] F(l i ) = F(f 1 (l i ), f 2 (l i ),..., f m (l i )) (2)

[0107] Among them, l i ∈L, L = {l 1 , l 2 , l 3 , l 4 , l 5}

[0108] f 1 (l), f 2 (l),..., f m (l) are 24 attribute functions corresponding to the evaluation index set, that is, m = 24;

[0109] l i is the corresponding feasible autonomous level of the unmanned ground platform, that is, i = 5;

[0110] w j is the evaluation index weight, and the sum of the weights is 1, which can be obtained through the expert analytic hierarchy process, that is, j = 24.

[0111] When the user operator has different preferences, the personality tending to be risk-averse or conservative can be reflected by adjusting the weights;

[0112] Step S3: Perform normalization preprocessing on the attribute functions;

[0113] 4. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 3, wherein in the step S3, the normalization preprocessing method is as follows:

[0114] Among them, the environmental perception index and the task planning index are extremely large indexes, and the normalization formula is as follows:

[0115]

[0116] Among them, the platform status index and the user status index are extremely small indexes, and the normalization formula is as follows:

[0117]

[0118] Among them, f ij (l) is an attribute function; f ij (l) is the expected value of the attribute function, is the maximum value, is the minimum value.

[0119] Step S4: Construct an autonomous level decision matrix according to the normalized attribute function;

[0120] In the step S4, the autonomous level decision matrix is constructed as follows:

[0121] d j (l i , l j ) = f j (l i ) - f j (l j ) (5);

[0122] D 5×24 = {d ij} (6);

[0123] Among them, d ij is the j-th attribute value of the autonomous level i minus the j-th attribute value of the autonomous level j, indicating the degree of achievement of the j-th attribute value for measuring the autonomous level l j ; D i represents the decision matrix with an autonomous level of 5 and 24 attribute quantities composed of d 5×24 , where R ij is obtained from formulas (3) and (4); ij is f ij (l) in the autonomous level decision matrix.

[0124] Step S5: Construct a priority function according to the autonomous level decision matrix;

[0125] In step S5, in multi-attribute decision-making, the priority degree between each pair of autonomous levels is calculated through a defined priority function, and the priority function is as follows:

[0126] If d ij ≤d kj , its value is 0; otherwise it is d j (l i , l j ), that is:

[0127]

[0128] where P(l i , l k ) is the priority degree of the attribute value.

[0129] Step S6: According to the priority function, compare the priority rankings to obtain the ranking of autonomous levels.

[0130] In step S6, according to the priority function, the comparison sorting index is:

[0131]

[0132] For indicators l i , l j ∈L, the weight values of individual attributes are w j , j = 1, 2,..., 24, ∏(l i , l k ) represents the directed attribute value of autonomous level l i , l k from l i to l k ;

[0133] Define the net inflow value φ(l i ) of autonomous level i as follows:

[0134]

[0135] By comparing the net flow magnitudes of each autonomous level, the level sorting relationship can be determined; if φ(l i ) > φ(l k ), the level of l i is higher than that of l k ; if φ(l i ) < φ(l k ), the level of l i is lower than that of l k , thus completing the ranking of feasible autonomous levels.

[0136] In summary, the solution proposed by the present invention addresses the problems of the single existing method for evaluating the autonomous decision-making of unmanned systems and the high difficulty of dynamic real-time solution. This paper proposes an evaluation method for the autonomous intelligent decision-making ability of unmanned platforms for human-machine collaboration, aiming to adapt to different environmental scenarios and different types of platforms, effectively combine operators and unmanned platforms, maximize the skill experience of operators and the combined efficiency of unmanned platforms, and improve the task completion rate.

[0137] Embodiment 2:

[0138] As Figure 3 shown, Embodiment 2 also provides an evaluation method for the autonomous decision-making ability of unmanned platforms.

[0139] Step 1: Design evaluation indicators for the autonomous decision-making ability of unmanned platforms; For the requirements of high-efficiency human-machine collaboration, dedicated indicator design is required for the evaluation of the autonomous decision-making ability of unmanned platforms, as follows:

[0140] Environmental perception indicators reflect the perception ability of the environment where the task is completed, including static geographical environment and dynamic situation environment. The environmental complexity seriously affects the intelligence level of unmanned ground vehicles. It includes attribute indicators such as road detection and tracking ability, dynamic collision avoidance ability, meteorological perception ability, threat level of the battlefield environment, the number of our own clusters, and the number of other parties' clusters.

[0141] Task planning indicators reflect the planning ability for tasks and actions, including task planning ability and action planning ability, which directly affect the tasks and actions that can be executed by unmanned ground platforms. It includes attribute indicators such as task level (formation / independent), task type, task planning duration, task path planning ability, and parking planning ability.

[0142] Platform status indicators reflect the ability level of the platform itself and the loaded payload, including the inherent ability level of the platform and the loaded equipment ability, which directly affect the hard kill ability and the survival ability of the unmanned platform. It includes attribute indicators such as platform tonnage level, loaded payload level, number of loaded payloads, and damage status level.

[0143] User status indicators reflect the ability level of users, including user qualification level and user individual status, which directly affect the efficiency of human-machine collaborative interaction. It includes attribute indicators such as user skill level, user historical evaluation level, and user interaction duration.

[0144] Considering the importance of the task, task planning and platform status indicators are more important than environmental perception and user status indicators, and their indicator attribute weight values are correspondingly higher.

[0145] Based on obtaining the parameter attributes of the above evaluation indicators, a comprehensive autonomous level influence data set is constructed to support the evaluation of the autonomous decision-making ability of unmanned platforms. The constrained multi-objective ability evaluation model under typical finite scenarios is as follows:

[0146]

[0147]

[0148] Among them, \(x\) is the evaluation plan, \(f(x)\) is the multi-objective evaluation function, \(g\) k (x), \(h\) s (x) are evaluation constraint functions; DR is the optimal evaluation plan.

[0149] Step 2: According to the evaluation indicators, establish a target decision-making ability function model to obtain the attribute function; Target decision-making ability function modeling:

[0150] The autonomous level decision function based on decision evaluation indicators is as follows:

[0151] F(l i ) = F(f 1 (l i ), f 2 (l i ),..., f m (l i )) (2)

[0152] Among them, \(l\) i ∈L, L = {l 1 , l 2 , l 3 , l 4 , l 5}

[0153] f 1 (l), f 2 (l),..., f m (l) are 24 attribute functions corresponding to the index set, that is, m = 24.

[0154] l i is the feasible autonomous level corresponding to the unmanned ground platform, that is, i = 5.

[0155] w j is the evaluation index weight, and the sum of the weights is 1, which can be obtained through the expert analytic hierarchy process, that is, j = 24. When the user operator has different preferences, their personality tending to be risk-averse or conservative can be reflected by adjusting the weights.

[0156] Step 3: Perform normalization preprocessing on the attribute function, and perform positive normalization preprocessing on the attribute values of the ability evaluation indicators;

[0157] The environmental indicators and task indicator attributes are extremely large (benefit type) indicators, and the larger the attribute value of the expected function, the better. The normalization formula is as follows:

[0158]

[0159] f ij (x) is the attribute function of the selected indicator. f ij (l) is the expected value of the attribute function of the selected indicator, is the maximum value, is the minimum value.

[0160] For the platform, the user indicator attribute is an extremely small (cost type) indicator, and the smaller the attribute value of the expected function, the better. The normalization formula is as follows:

[0161]

[0162] Step 4: Construct an autonomous level decision matrix based on the normalized attribute function; construction of the autonomous decision-making ability matrix;

[0163] Based on the normalization of the evaluation indicator attributes, construct an autonomous level decision matrix.

[0164] d j (l i ,l j ) = f j (l i ) - f j (l j ) (5)

[0165] D 5×24 = {d ij} (6)

[0166] d ij is the j-th attribute value of autonomous level i minus the j-th attribute value of autonomous level j, indicating the degree of achievement of the j-th attribute value of autonomous level l measured by the attribute function f j . D i represents the decision matrix with autonomous level 5 and 24 attribute quantities composed of d 5×24 . ij

[0167] Step 5: Construct a preference function based on the autonomous level decision matrix; construction of the pairwise comparison preference function of the decision-making ability matrix;

[0168] In multi-attribute decision-making, the preference degree between each pair of autonomous levels is calculated through the defined preference function. P(l i ,l k ) represents the preference degree function for comparing autonomous level i and autonomous level k. ​

[0169] P(l i ,l k ) = f j (d j (l i ,l j )) (7)

[0170] If d ij ≤ d kj , its value is 0; otherwise it is d j (l i ,l j ). That is:

[0171]

[0172] Where P(l i ,l k ) is the priority of the attribute value.

[0173] Step Six: According to the priority function, compare the priority rankings to obtain the ranking of the autonomy levels; conduct a directed comparison of the decision-making capabilities for priority ranking;

[0174] According to the priority function, the comparison sorting index is:

[0175]

[0176] For the indicator l i ,l j ∈ L, the weight values of individual attributes are w j, j = 1, 2,..., 24. ∏(l i ,l k ) represents the directed attribute value of the autonomy level l i ,l k from l i to l k .

[0177] Define the net inflow value φ(l i ) of the autonomy level i. As follows:

[0178]

[0179] By comparing the net flow magnitudes of each autonomy level, the level ranking relationship can be determined. If φ(l i ) > φ(l k ),l i the level is higher than l k ; if φ(l i ) < φ(l k ),l i the level is lower than l k , thus completing the ranking of the feasible autonomy levels.

[0180] In view of the requirements for the unmanned platform to perform tasks in complex environments, considering the current situation of the complex environment of the unmanned platform, limited continuous operation time, and low fully autonomous intelligent decision-making and control capabilities, this application proposes an algorithm for evaluating the autonomous decision-making ability of the unmanned platform for high-efficiency human-machine collaboration. This algorithm can complete the evaluation of the autonomous intelligent decision-making ability for tasks in typical complex environments, achieving the goal of effectively improving the task completion rate of the unmanned platform.

[0181] In view of the problem that the user participation degree of the unmanned platform is high and the autonomy of the unmanned platform cannot be effectively exerted under complex environments and high-level task execution requirements, this application proposes a method for evaluating the autonomous decision-making ability of the unmanned platform for high-efficiency human-machine collaboration, which can adapt to different environmental scenarios, be applied to different types of unmanned platforms, realize the evaluation of the autonomous decision-making ability of the unmanned platform for user capabilities, reduce the workload of users, improve the robustness of the task execution of the unmanned platform, and effectively promote the maximization of the human-machine fusion and collaboration effect.

[0182] Embodiment 3:

[0183] The present invention discloses a system for evaluating the autonomous decision-making ability of an unmanned platform. Figure 4 FIG. is a structural diagram of a system for evaluating the autonomous decision-making ability of an unmanned platform according to an embodiment of the present invention; as Figure 4 shown, the system 100 includes:

[0184] A first processing module 101, configured to design evaluation indicators for the autonomous decision-making ability of the unmanned platform;

[0185] A second processing module 102, configured to establish a target decision-making ability function model according to the evaluation indicators to obtain an attribute function;

[0186] A third processing module 103, configured to perform normalization preprocessing on the attribute function;

[0187] A fourth processing module 104, configured to construct an autonomous level decision matrix according to the normalized attribute function;

[0188] A fifth processing module 105, configured to construct a priority function according to the autonomous level decision matrix;

[0189] A sixth processing module 105, configured to compare the priority rankings according to the priority function to obtain the ranking of the autonomous levels.

[0190] According to the system of the second aspect of the present invention, the first processing module 101 is specifically configured that the evaluation indicators include environmental perception indicators, task planning indicators, platform status indicators, and user status indicators;

[0191] The environmental perception indicators include geographical environment indicators and situation environment indicators. Among them, the geographical environment indicators include the road detection and tracking ability level, the dynamic collision avoidance ability level, and the meteorological perception ability level; the situation environment indicators include the battlefield environment threat level, the number of our clusters, and the number of other clusters;

[0192] The mission planning indicators include mission planning indicators and action planning indicators. Among them, the mission planning indicators include the mission level, the mission type, the mission planning duration level, and the number of mission participants; the action planning indicators include the mission path planning ability level, the obstacle avoidance planning ability level, and the parking planning ability level;

[0193] The platform status indicators include the platform ability level and the platform real-time status indicators. Among them, the platform ability level includes the platform tonnage level, the platform load level, and the platform cooperation management level; the platform real-time status indicators include the loaded weapon level, the number of loaded weapons, and the damage status level;

[0194] The user status indicators include the user qualification level indicators and the user individual status indicators. Among them, the user qualification level indicators include the user skill level, the historical evaluation level for the user, and the user operation proficiency;

[0195] The user individual status indicators include the user interaction duration and the user mental state level.

[0196] According to the system of the second aspect of the present invention, the second processing module 102 is specifically configured such that the target decision-making ability function model is:

[0197] F(l i ) = F(f 1 (l i ), f 2 (l i ),..., f m (l i )) (2)

[0198] Wherein, l i ∈L, L = {l 1 , l 2 , l 3 , l 4 , l 5},

[0199] f 1 (l), f 2 (l),..., f m (l) are 24 attribute functions corresponding to the evaluation index set, that is, m = 24;

[0200] l iIt corresponds to the feasible autonomy level of the unmanned ground platform, i.e., i = 5;

[0201] w j It is the weight of the evaluation index, and the sum of the weights is 1, which can be obtained through the expert analytic hierarchy process, i.e., j = 24.

[0202] When the preferences of the user operator are different, the personality tending to be risk - type or conservative - type can be reflected by adjusting the weights.

[0203] According to the system of the second aspect of the present invention, the third processing module 103 is specifically configured as follows for the normalization pre - processing:

[0204] Among them, the environmental perception index and the task planning index are extremely large - type indexes, and the normalization formula is as follows:

[0205]

[0206] Among them, the platform status index and the user status index are extremely small - type indexes, and the normalization formula is as follows:

[0207]

[0208] Among them, f ij (l) is the attribute function; f ij (l) is the expected value of the attribute function, is the maximum value, is the minimum value.

[0209] According to the system of the second aspect of the present invention, the fourth processing module 104 is specifically configured to construct an autonomy level decision matrix as follows:

[0210] d j (l i , l j ) = f j (l i ) - f j (l j ) (5);

[0211] D 5×24 = {d ij}} (6);

[0212] Among them, d ij is the j - th attribute value of the autonomy level i minus the j - th attribute value of the autonomy level j, indicating the degree of achievement of the j - th attribute value of the autonomy level l j measured by the attribute function f i ; D 5×24 represents the decision matrix with the autonomy level of 5 and the number of attributes of 24 composed of d ij , where the R ijFor f in the autonomous level decision matrix ij (l).

[0213] According to the system of the second aspect of the present invention, the fifth processing module 105 is specifically configured that, in multi-attribute decision-making, the priority degree between each pair of autonomous levels is calculated by a defined priority function, and the priority function is as follows:

[0214] If d ij ≤d kj , its value is 0; otherwise it is d j (l i , l j ), that is:

[0215]

[0216] Where P(l i , l k ) is the priority degree of the attribute value.

[0217] According to the system of the second aspect of the present invention, the sixth processing module 106 is specifically configured to, according to the priority function, the comparison sorting index is:

[0218]

[0219] Index l i , l j ∈L, the weight values of individual attributes are respectively w j , j = 1, 2,..., 24, ∏(l i , l k ) represents the directed attribute value of the autonomous level l i , l k from l i pointing to l k ;

[0220] Define the net inflow value φ(l i ) of the autonomous level i as follows:

[0221]

[0222] By comparing the net flow magnitudes of each autonomous level, the level sorting relationship can be determined; if φ(l i ) > φ(l k ), the level of l i is higher than that of l k ; if φ(l i ) < φ(l k ), the level of l i is lower than that of l k , thereby completing the sorting of the feasible autonomous levels.

[0223] Example 4:

[0224] This application discloses an electronic device. The electronic device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps in any one of the unmanned platform autonomous decision-making ability evaluation methods in the disclosed Embodiment 1 of the present invention are implemented.

[0225] Figure 5 As shown in the structure diagram of an electronic device according to an embodiment of the present invention, Figure 5 the electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, near field communication (NFC), or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the electronic device, or an external keyboard, touchpad, or mouse, etc.

[0226] Those skilled in the art can understand that Figure 5 the structure shown in is only a structure diagram of a part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the solution of this application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0227] Example 5:

[0228] The present invention discloses a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the steps in any one of the unmanned platform autonomous decision-making ability evaluation methods in Embodiment 1 of the present invention are implemented.

[0229] Please note that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification. The above embodiments only represent several implementation manners of the present application, and their descriptions are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

[0230] The embodiments of the subject matter and the functional operations described in this specification can be implemented in the following: digital electronic circuits, tangible computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules in computer program instructions encoded on a tangible non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions can be encoded on a machine-generated propagated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for execution by the data processing device. A computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0231] The processes and logical flows described in this specification can be executed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logical flows can also be executed by dedicated logic circuits, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuits.

[0232] Computers suitable for executing computer programs include, for example, general and / or special-purpose microprocessors, or any other type of central processing unit. Generally, the central processing unit will receive instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, etc., or the computer will be operably coupled to such mass storage devices to receive data therefrom or transfer data thereto, or both. However, a computer is not necessarily required to have such devices. In addition, a computer may be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name just a few examples.

[0233] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as including semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special logic circuitry.

[0234] Although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of what is claimed, but rather as mainly describing the features of specific embodiments of a particular invention. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may operate in certain combinations as described above and even be initially claimed as such, one or more features from a claimed combination may in some cases be removed from that combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination.

[0235] Similarly, although operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or sequentially, or that all illustrated operations be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0236] Accordingly, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the acts recited in the claims can be performed in a different order and still achieve the desired result. Further, the processes depicted in the figures are not necessarily shown in the particular order or sequential order to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0237] The foregoing are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for evaluating the autonomous decision-making capability of an unmanned platform, characterized in that: include: Step S1, designing evaluation indicators for autonomous decision-making capabilities of unmanned platforms; Step S2: Establish a target strategy capability function model based on the evaluation index to obtain the attribute function; Step S3, performing normalization preprocessing on the attribute function; Step S4: construct an autonomous level decision matrix according to the normalized attribute function; Step S5: constructing a priority function according to the autonomous level decision matrix; Step S6: Compare the priority rankings according to the priority function to obtain the ranking of the autonomous levels.

2. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 1, characterized in that: In the step S1, the evaluation index includes an environmental perception index, a task planning index, a platform status index and a user status index; The environmental perception indicators include geographical environmental indicators and situational environmental indicators, wherein the geographical environmental indicators include the road detection and tracking capability level, the dynamic collision avoidance capability level and the meteorological perception capability level; the situational environmental indicators include the battlefield environmental threat level, the number of our own clusters and the number of other clusters; The task planning indicators include task planning indicators and action planning indicators, wherein the task planning indicators include task level, task type, task planning duration level and number of task participants; the action planning indicators include task path planning capability level, obstacle avoidance planning capability level and parking planning capability level; The platform status indicators include platform capability levels and indicators and platform real-time status indicators, wherein the platform capability level includes platform tonnage level, platform load level and platform collaborative management level; the platform real-time status indicators include loaded weapon level, loaded weapon quantity and damage status level; The user status indicators include user experience level indicators and user individual status indicators, wherein the user experience level indicators include user skill level grades, historical evaluation grades and user operation proficiency; The user individual status indicators include user interaction duration and user mental state level.

3. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 2 is characterized in that: In step S2, the target strategy capability function model is: F(l i )=F(f1(l i ),f2(l i ),...,f m (the i )) (2) in, f1(l),f2(l),...,f m (l) is the 24 attribute functions corresponding to the evaluation index set, i.e., m = 24; l i It corresponds to the feasible autonomy level of the unmanned ground platform, i.e., i = 5; w j is the evaluation index weight, and the sum of the weights is 1, which can be obtained through the expert hierarchy analysis method, that is, j = 24.

4. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 3 is characterized in that: In step S3, the normalization preprocessing method is as follows: Among them, the environmental perception index and task planning index are extremely large indicators, and the normalized formula is as follows: Among them, the platform status indicator and user status indicator are extremely small indicators, and the normalization formula is as follows: Among them, f ij (l) is the attribute function; f ij (l) is the expected value of the attribute function, is the maximum value, is the minimum value.

5. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 4 is characterized in that: In step S4, the autonomous level decision matrix is ​​constructed as follows: d j (l i ,l j )=f j (l i )-f j (l j ) (5); D 5×24 ={d ij } (6); Among them, d ij = is the j attribute value of autonomy level i minus the j attribute value of autonomy level j, expressed by the attribute function f j Measuring the level of autonomy i The achievement degree of the j-th attribute value; D 5×24 Indicated by d ij The decision matrix with 5 autonomy levels and 24 attributes is constructed, where formulas (3) and (4) are used to obtain R ij is f in the autonomous level decision matrix ij (l).

6. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 5 is characterized in that: In step S5, in the multi-attribute decision making, the priority between each pair of autonomy levels is calculated by a defined priority function, and the priority function is as follows: If d ij ≤d kj , its value is 0; otherwise it is d j (l i , l j ),Right now: Where P(l i , l k ) is the priority of the attribute value.

7. The method for evaluating the autonomous decision-making ability of an unmanned platform according to claim 6 is characterized in that: In step S6, according to the priority function, the comparison ranking index is: Indicator i , l j ∈L, the weight values ​​of a single attribute are w j ,j=1,2,...,24,Π(l i , l k ) indicates the autonomy level l i , l k By l i Point to l k The directed attribute value of ; Define the net inflow value φ(l i ),as follows: By comparing the net flow size of each main level, the level ranking relationship can be determined; if φ(l i )>φ(l k ), l i Level higher than l k ; If φ(l i )<φ(l k ), l i Level below l k , and then complete the ranking of feasible autonomy levels.

8. A method system for evaluating the autonomous decision-making ability of an unmanned platform, characterized in that: The system comprises: The first processing module is configured to design an evaluation index of the autonomous decision-making capability of the unmanned platform; The second processing module is configured to establish a target strategy capability function model according to the evaluation index to obtain an attribute function; A third processing module is configured to perform normalization preprocessing on the attribute function; The fourth processing module is configured to construct an autonomous level decision matrix according to the normalized attribute function; a fifth processing module configured to construct a priority function according to the autonomy level decision matrix; The sixth processing module is configured to compare the priority rankings according to the priority function to obtain the ranking of the autonomy level.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in the method for evaluating the autonomous decision-making capability of an unmanned platform described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps in the method for evaluating the autonomous decision-making capability of an unmanned platform described in any one of claims 1 to 7 are implemented.

Images